Models
Anthropic
Terminal-Bench AI Model Scores

@ArtificialAnlysX · Sep 28, 2026

Terminal-Bench AI Model Scores

@ArtificialAnlys's benchmark bar chart drew 23.2K views on X: 2.0x @artificialanlys's median post and #690 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Terminal-Bench 4.0 and 0.0 AI Model Scores

XData Benchmark bar chart Claude Sonnet 5 All Anthropic models GPT-4.1 Gemini 2.5 Pro o4-mini DeepSeek-R1Claude 4 OpusClaude 4 Sonnet

@ArtificialAnlys: Terminal-Bench AI Model Scores — Published by @ArtificialAnlys on X, Sep 28, 2026. Source: x.com

37/ 100

ViralChart score

Quiet

Fewer views and a lower engagement rate than the median post.

#787 of 1,162 AI chart posts we hold · #237 of 491 @artificialanlys posts. Score = views 40%, likes 30%, engagement rate 15%, save rate 15%, each as a percentile of every AI chart post we hold.

Our read

It sits in the Quiet quadrant, with a score rank of #787 of 1,162 AI chart posts.

Its save rate of 0.035% sits at the 17th percentile among AI chart posts, below the 0.076% median.

The post landed at #3 of 6 by views among @ArtificialAnlys posts that day.

At 23.2K views it ran 2x the company median of 11.4K, ranking #197 of 491 @ArtificialAnlys posts.

6posts from @artificialanlys that day

Part of a run of 6 posts on Sep 28, 2026. This one was #3 of 6 by views that day.

bottom 17%save rate

0.035% of viewers bookmarked it to come back to. The median post gets 0.076%.

2.0x@artificialanlys's median post

23.2K views, where @artificialanlys's typical post gets 11.4K.

0.5xthe median benchmark bar chart post

Across 215 benchmark bar chart posts we hold, the median gets 44.4K views.

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 491 from @artificialanlys.

Where it sits

Reach against resonance

Each dot is a post. Right is more views, up is a higher engagement rate. The lines are the medians, so the four corners are the four kinds of post.

Among 1,162 AI chart posts we hold

Score #787 of 1,162

Views	23.2K	#690	bottom 41%
Likes	143	#717	bottom 38%
Engagement rate	0.67%	#643	bottom 45%
Save rate	0.035%	#963	bottom 17%

Among 491 @artificialanlys posts

Score #237 of 491

Views	23.2K	#197	top 40%
Likes	143	#212	top 43%
Engagement rate	0.67%	#313	bottom 36%
Save rate	0.035%	#393	bottom 20%

Growth

One read so far

Views23.2K

Age at our read14 days

Views per day of life1.6Kviews divided by days since it was posted

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

@artificialanlys's posts over time

Every post from this account we hold, by date and views. This one is marked; the line is the running median of the last 10.

News · Sep 28, 2026

@ArtificialAnlys posts Terminal-Bench AI model scores chart

A benchmark bar chart on Terminal-Bench 4.0 and 0.0 scores drew 23.2K views and a 0.035% save rate.

What happened

@ArtificialAnlys posted a benchmark bar chart on Terminal-Bench 4.0 and 0.0 AI model scores on September 28, 2026. It was one of 6 posts from the account that day, alongside 5 others.

The numbers

It reached 23.2K views, ranking #690 of 1,162 AI chart posts and #197 of 491 @ArtificialAnlys posts. Its score rank was #787 of 1,162 AI chart posts.

The lesson

A save rate of 0.035% against the 0.076% median among AI chart posts shows this benchmark bar chart was not kept for citation. The 6 models shown did not convert into saves.

What it means

At #197 of 491 @ArtificialAnlys posts by views, this chart beat the company median of 11.4K views by 2x. Its save rate of 0.035% against the 0.076% median among AI chart posts shows the reach did not carry into bookmarks.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what @artificialanlys posted next

Data and API

36 points read off this chart

Estimated from the image 30%

Series	Group	Value	Read
Terminal-Bench 4.0	Claude Sonnet 4.5 (with Scratchpad)	63.6 %	estimated
Terminal-Bench-Science 0.1	Claude Sonnet 4.5 (with Scratchpad)	63.3 %	estimated
Terminal-Bench 4.0	Claude Opus 4.5 (with Scratchpad)	59.6 %	estimated
Terminal-Bench-Science 0.1	Claude Opus 4.5 (with Scratchpad)	59 %	estimated
Terminal-Bench 4.0	Claude Sonnet 4.5 (with Scratchpad)	59.1 %	estimated
Terminal-Bench-Science 0.1	Claude Sonnet 4.5 (with Scratchpad)	53.3 %	estimated
Terminal-Bench 4.0	GPT-5.1 (High)	52 %	estimated
Terminal-Bench-Science 0.1	GPT-5.1 (High)	43.3 %	estimated
Terminal-Bench 4.0	Claude Opus 4.5 (with Scratchpad)	43.9 %	estimated
Terminal-Bench-Science 0.1	Claude Opus 4.5 (with Scratchpad)	30 %	estimated
Terminal-Bench 4.0	GPT-5.1 (High)	41.9 %	estimated
Terminal-Bench-Science 0.1	GPT-5.1 (High)	11.9 %	estimated

Showing 12 of 36. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/f7b165ee0f22.json
GET https://viral-chart.com/api/charts/f7b165ee0f22.json
GET https://viral-chart.com/api/charts/f7b165ee0f22.skill.md

Make one like this Open the post JSON Chart data JSON Skill file API docs

Static files in this prototype. The post JSON holds the public numbers, ranks, score, quadrant, our reads and, when checked, our copy.

API · Max

Use this chart via API

On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id f7b165ee0f22.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.30 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/f7b165ee0f22`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/f7b165ee0f22/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/f7b165ee0f22/render?view=1`	The draw-only view this page uses	Open
POST	`/mcp`	Tool get_chart_data with this id, for Claude, Cursor and other agents	Max

curlMax

curl -s https://viral-chart.com/api/v1/charts/f7b165ee0f22/data \
  -H "Authorization: Bearer $VIRALCHART_KEY"

Claude CodeMax

claude mcp add --transport http viralchart https://viral-chart.com/mcp \
  --header "Authorization: Bearer $VIRALCHART_KEY"

60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.

More charts about Claude Sonnet 5

Claude Sonnet 5: API value per dollar: OpenAI vs Anthropic

X · @SemiAnalysis_Oct 5, 2026

API value per dollar: OpenAI vs Anthropic22.4K views · 90 likes